I am using deep speech for speech to text. Up to 0.8.1, when I ran transcriptions like:
byte_encoding = subprocess.check_output(
"deepspeech --model deepspeech-0.8.1-models.pbmm --scorer deepspeech-0.8.1-models.scorer --audio audio/2830-3980-0043.wav", shell=True)
transcription = byte_encoding.decode("utf-8").rstrip("\n")
I would get back results that were pretty good. But since 0.8.2, where the scorer argument was removed, my results are just rife with misspellings that make me think I am now getting a character level model where I used to get a word-level model. The errors are in a direction that looks like the model isn't correctly specified somehow.
Now I when I call:
byte_encoding = subprocess.check_output(
['deepspeech', '--model', 'deepspeech-0.8.2-models.pbmm', '--audio', myfile])
transcription = byte_encoding.decode("utf-8").rstrip("\n")
I now see errors like
endless -> "endules"
service -> "servic"
legacy -> "legaci"
earning -> "erting"
before -> "befir"
I'm not 100% that it is related to removing the scorer from the API, but it is one thing I see changing between releases, and the documentation suggested accuracy improvements in particular.
Short: The scorer matches letter output from the audio to actual words. You shouldn't leave it out.
Long: If you leave out the scorer argument, you won't be able to detect real world sentences as it matches the output from the acoustic model to words and word combinations present in the textual language model that is part of the scorer. And bear in mind that each scorer has specific lm_alpha and lm_beta values that make the search even more accurate.
The 0.8.2 version should be able to take the scorer argument. Otherwise update to 0.9.0, which has it as well. Maybe your environment is changed in a way. I would start in a new dir and venv.
Assuming you are using Python, you could add this to your code:
ds.enableExternalScorer(args.scorer)
ds.setScorerAlphaBeta(args.lm_alpha, args.lm_beta)
And check the example script.
Related
So I have created a huge screen that essentially just shows the robot status for every robot in this factory (individually)… At the very end of the project, they decided they want one object on the screen that blinks if any of the 300 robots fault. I am trying to think of a way to make this work. Maybe a global script of some kind? Problem is, I do not do much scripting in Cimplicity, so any help is appreciated.
All the points that are currently used on this screen (to indicate a fault) have very similar names… as in, the beginning is the same… so I was thinking of a script that could maybe recognize if a bit is high based on PART of it's string name characteristic. The end will change a little each time, but I am sure there is a way to only look for part of a string and negate the rest. If the end has to be hard coded, that's fine.
You can use a Python script in Cimplicity.
I will not go into detail on the use of python in Cimplicity, which is well described in the documentation indicated above.
Here's an example of what can be done... note that I don't have a way to test it and, of course, this will work if the name of your robots in the declaration follows the format Robot_1, Robot_2, Robot_3 ... Robot_10 ... Robot_300 and it also depends on the Name and the Type of the fault variable... as you didn't define it, I imagine it can be an integer, with ZERO indicating no error. But if you use something other than that, you can easily change it.
import cimplicity
(...)
OneRobotWithFault = False
# Here you get the values and check for fault
for i in range(0, 300):
pointName = f'MyFactory.Robot_{i}.FaultCode'
robotFaultCode = cimplicity.point_get(pointName)
if robotFaultCode > 0:
OneRobotWithFault = True
break
# Set the status to the variable "WeHaveRobotWithFault"
cimplicity.point_set("WeHaveRobotWithFault", OneRobotWithFault)
I'm trying to test the model (model.bin) i've made with fastText on a test file (test.txt). In this test file, i have 135 labelised data. I'm expecting from fastText to test my model on this number of example, but instead, it only test it over 1 example. Where does come from this problem ?
I've already tried to do such a thing with another model and another testing file and all worked nicely.
this is how I test my model. model_baby.bin is the model, and test.data.txt is my testing file.
./fasttext test model_baby.bin test.data.txt
N 1
P#1 1
R#1 0.0164
Number of examples: 1
And here is an extract from my testing file
__label__4.0 I love the fact you can hide your stuff. Only down is that the straps to hold it at midpoint and bottom could be better designed for your car. It's got plenty of room which is great. __label__5.0 This hid our ipad wonderfully. Especially for those quick stops where we all had jump out and use the restroom. It zipped, folded and held all our stuff for the kids in the back seat. __label__3.0
As i have more than 1 labelised example in my testing file, I expect the output "Number of examples: " to be at least more than 1 but the actual one is "1"
From the official documentation (https://fasttext.cc/docs/en/supervised-tutorial.html): Each line of the text file contains a list of labels, followed by the corresponding document. All the labels start by the __label__ prefix, which is how fastText recognize what is a label or what is a word.
I don't understand very much your extract. I think it should be like this:
__label__4.0 I love the fact you can hide your stuff. Only down is that the straps to hold it at midpoint and bottom could be better designed for your car. It's got plenty of room which is great.
__label__5.0 This hid our ipad wonderfully. Especially for those quick stops where we all had jump out and use the restroom. It zipped, folded and held all our stuff for the kids in the back seat.
__label__3.0 ...
Among many distressing graphics changes to r2014b, the Plot Browser now only displays a certain number of lines per plot (looks like the limit is 50). Any number of plots above this limit are not displayed in the Plot Browser - it just says "and 78 more..."
Is there anyway to remove the limit? I want to see all my lines in the plot browser.
Unfortunately the answer is currenty:
No you cannot remove this limit
This was already reported to mathworks a while ago, and here is the reply:
I am writing in reference to your Technical Support Case #01143663
regarding 'plot browser with "and xxxx more...." indication'.
Really interesting question (and even a bit surprising). Basically
this limitation has been introduced with MATLAB 2014b!
Our developers are aware of that, and they are working to solve it. An
enhancement/bug request has been already submitted, and I am going to
add this case to the list. However, I cannot guarantee you a release
date.
If you think this limitation is crucial for your work, I would
strongly suggest you to contact your account manager, which will have
a bit more influence on the developers than a simple engineer :).
Of course, if there is anything else I can do for you, please let me
know
So it seems that you will have to deal with this limitation if you keep using 2014b.
This was also an issue for me; in particular I wanted to see the DisplayName property of the graphics object in the list. I used a workaround where I created a callback function, so that when clicking on a data point, the DisplayName would be shown. This can be helpful if you have a plot of many lines and want to see the DisplayName of a particular one. You would first need to set the DisplayName property of the graphics objects for this to work, as it's empty by default. You could also use this to show other properties, such as Color or LineStyle, that are shown in the plot browser:
%Based on
%http://www.mathworks.com/help/matlab/ref/datacursormode.html
%'fig_h' is the figure handle
dcm_obj = datacursormode(fig_h);
set(dcm_obj,'UpdateFcn',#myupdatefcn)
And then include this function as a separate file on the Matlab path, or paste into the function you're currently writing, and include an extra 'end' at the end of that function:
function name = myupdatefcn(empt,event_obj)
% Customizes text of data tips
tar = get(event_obj,'Target');
name = get(tar,'DisplayName');
end
I writing editor with netbeans7 and ANTLR4
I have line in my.g4 file
Label : {(getCharPositionInLine()==0)}? ID;
That works well for static files, but while editing getCharPositionInLine() returns 0 often in other places.
How get a real position in lexer?
updated
I created example with this problem
https://github.com/daimor/SimpleANTLR
Your error is likely in the way you are constructing your lexer and/or input stream (i.e. code that you have not shown here). The predicate you describe above will work as expected for an ANTLR 4 lexer.
Also, if getCharPositionInLine()==0, then exactly one of the following conditions is also true:
_input.index()==0
_input.LA(-1)=='\n'
I'm struggling with Solr search Arabic for several days and made some experiment. Here is the simple reflection of the problem.
After I store some Arabic sentence (now only 1 word السوري ) into database and have Solr index it, then query it by q=*:*&wt=python,(if no wt part, it was garbled chars) the response is:
'\u00d8\u00a7\u00d9\u201e\u00d8\u00b3\u00d9\u02c6\u00d8\u00b1\u00d9\u0160'
The actual word I store there for index is coding in another way:
'\xd8\xa7\xd9\x84\xd8\xb3\xd9\x88\xd8\xb1\xd9\x8a'
As you can tell, there is a one-to-to corresponding from \xd8↔\u00d8. But I don't know what is the name of this coding, thus I cannot convert it. And when I do the search as: <>/select/?q=السوري&wt=python,the response is:
{'responseHeader':{'status':0,'QTime':0,'params':{'wt':'python','q':u'\u0627\u0644\u0633\u0648\u0631\u064a'}},'response':{'numFound':0,'start':0,'docs':[]}}
No docs found and it seems using a third version for coding u'\u0627\u0644\u0633\u0648\u0631\u064a'. if I take it and encode('utf8') then it convert back to '\xd8\xa7\xd9\x84\xd8\xb3\xd9\x88\xd8\xb1\xd9\x8a'.
In summary, when it (السوري) is in my code (python) or in data base (mysql),
it presents as 'form1':
'\xd8\xa7\xd9\x84\xd8\xb3\xd9\x88\xd8\xb1\xd9\x8a'
When it is indexed by Solr, it converts to form2:
'\u00d8\u00a7\u00d9\u201e\u00d8\u00b3\u00d9\u02c6\u00d8\u00b1\u00d9\u0160'
And when I use <>/select/?q=السوري&wt=python, to query from browser (Google chrome), it becomes form3:
'\u0627\u0644\u0633\u0648\u0631\u064a'
(which could convert back to form1 by encode('utf8') But since they are different, the search matches nothing.
Therefore, those three different encode strategy may be the core problem. Could anyone help me figure it out and solve the search problem?
Thanks in advance.